执行SQL更新语句（INSERT、UPDATE、DELETE）
AI agents call execute_update to permanently remove resources in SQLite MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool executes arbitrary SQL DML statements including DELETE, which can irreversibly destroy data. Since it permits DELETE (and potentially DROP if not restricted), it falls under Destructive. The blast radius is critical because a malicious or erroneous query could wipe entire tables or databases with no built-in undo mechanism.
From the tool's definition 执行SQL更新语句（INSERT、UPDATE、DELETE）— explicitly includes DELETE operations
Attacks that exploit this kind of access
执行SQL更新语句（INSERT、UPDATE、DELETE）. It is categorised as a Destructive tool in the SQLite MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the SQLite MCP Server MCP server in PolicyLayer and add a rule for execute_update: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches SQLite MCP Server. Nothing to install.
execute_update is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the execute_update rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for execute_update. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
execute_update is provided by the SQLite MCP Server MCP server (rikxed/sqlite-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →